Robinson Ferrer Damla Turgut Zhongzhou Chen Shashank Sonkar When Can We Trust LLM Graders? Calibrating Confidence for Automated Assessment. AIED (1) 2026 385-399 conf/aied/2026-1 https://doi.org/10.1007/978-3-032-29744-0_26 db/conf/aied/aied2026-1.html#FerrerTCS26 streams/conf/aied